From: Christoph Hellwig <hch@lst.de>
To: Keith Busch <kbusch@kernel.org>
Cc: sagi@grimberg.me, linux-nvme@lists.infradead.org,
Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>,
hch@lst.de
Subject: Re: [PATCH] nvmet: allow block device to use buffered I/O
Date: Thu, 31 Oct 2019 15:42:47 +0100 [thread overview]
Message-ID: <20191031144247.GA6024@lst.de> (raw)
In-Reply-To: <20191030063609.GB16863@redsun51.ssa.fujisawa.hgst.com>
On Wed, Oct 30, 2019 at 03:36:09PM +0900, Keith Busch wrote:
> On Tue, Oct 29, 2019 at 09:26:23PM -0700, Chaitanya Kulkarni wrote:
> > NVMeOF target already has a support to execute requests in the
> > buffered I/O mode with file backend. This patch allows block devices
> > to be used with file backend code so that buffered I/O parameter can
> > be set for a block device backed namespace when newly introduce
> > configfs parameter use_vfs=1.
>
> Is the fs overhead so bad that we can't just remove the bio based nvme
> target? It seems low enough that having a single path to optimize is
> worth considering.
Once we go down bemchmarketing for latency and iops it matters, as it
is significantly less code and cachelines. The actual I/O pattern is
the same, so for more usual setups that do bigger I/O or have slower
devices they'll be mostly the same.
_______________________________________________
Linux-nvme mailing list
Linux-nvme@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-nvme
next prev parent reply other threads:[~2019-10-31 14:43 UTC|newest]
Thread overview: 6+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-10-30 4:26 [PATCH] nvmet: allow block device to use buffered I/O Chaitanya Kulkarni
2019-10-30 6:36 ` Keith Busch
2019-10-31 14:42 ` Christoph Hellwig [this message]
2019-10-31 14:45 ` Christoph Hellwig
2019-11-01 6:35 ` Chaitanya Kulkarni
2019-10-31 16:30 ` Sagi Grimberg
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20191031144247.GA6024@lst.de \
--to=hch@lst.de \
--cc=chaitanya.kulkarni@wdc.com \
--cc=kbusch@kernel.org \
--cc=linux-nvme@lists.infradead.org \
--cc=sagi@grimberg.me \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).